 |
POLICY SUBSTANCE IN THE PUBLIC MIND: The Issue Structure of Mass Politics
| |
| | Unformatted Document Text:
70
i
Because it treats each case equally in all calculations, AMOS (like LISREL) cannot handle weighted data
files. For the larger project of which this paper is a part, we felt it necessary, with the weighted NES samples of 1960, 1976, 1992, 1996, and 2000 to estimate covariance matrices of the relevant variables and then use these matrices as the input for AMOS. While list-wise deletion of data is customary in these kinds of analyses, its use would greatly reduce the number of cases here. Therefore, we replicated the CFA analysis for these years using covariance matrices based on pair-wise deletion of missing data. We also reran the CFAs on the unweighted individual-level data. Because the resulting coefficients were reliably similar, only the products of the unweighted data analyses are presented here for these years.
ii
While all five theoretically interpretable sub-dimensions did appear in the year 2000, they were so tightly
correlated that a single dimension could be argued to serve as an adequate fit to the data.
iii
It goes without saying that this is a giant step forward by comparison to measures that merely use the
same single item across time, since a) the latter sharply constricts the time period for most analyses—most items run for a few surveys only; b) it inherently limits the realms in which such analyses can be pursued—two of our four policy domains lack even a single such ‘marker item’; and c) by extension, it eliminates even the possibility of having a comprehensive, cross-domain issue context.
iv
We include 1948 in Table 1 because its findings are consistent with what follows about social welfare
and international relations. The 1948 survey, however, is best viewed as a kind of ‘pre-test’ for the NES in many regards, not least of which, for us, is that it lacks policy items on both civil rights and cultural values. We make only the most limited use of its results in the analysis that follows.
v
It would have been nice to have a counterpart analysis for one or more of the early postwar years, to be
sure that nothing had changed in the interim. Yet the fact that there are no counterpart items to behavioral welfare in this earlier period is itself an unobtrusive measure of the situation in its time: survey analysts were confident that ‘working-age welfare’ was what most people meant in the public debate over welfare policy.
|
| | Authors: Claggett, William. and Shafer, Byron. |
|
| |
|
|
70
i
Because it treats each case equally in all calculations, AMOS (like LISREL) cannot handle weighted data
files. For the larger project of which this paper is a part, we felt it necessary, with the weighted NES
samples of 1960, 1976, 1992, 1996, and 2000 to estimate covariance matrices of the relevant variables and
then use these matrices as the input for AMOS. While list-wise deletion of data is customary in these kinds
of analyses, its use would greatly reduce the number of cases here. Therefore, we replicated the CFA
analysis for these years using covariance matrices based on pair-wise deletion of missing data. We also
reran the CFAs on the unweighted individual-level data. Because the resulting coefficients were reliably
similar, only the products of the unweighted data analyses are presented here for these years.
ii
While all five theoretically interpretable sub-dimensions did appear in the year 2000, they were so tightly
correlated that a single dimension could be argued to serve as an adequate fit to the data.
iii
It goes without saying that this is a giant step forward by comparison to measures that merely use the
same single item across time, since a) the latter sharply constricts the time period for most analyses—most
items run for a few surveys only; b) it inherently limits the realms in which such analyses can be pursued—
two of our four policy domains lack even a single such ‘marker item’; and c) by extension, it eliminates
even the possibility of having a comprehensive, cross-domain issue context.
iv
We include 1948 in Table 1 because its findings are consistent with what follows about social welfare
and international relations. The 1948 survey, however, is best viewed as a kind of ‘pre-test’ for the NES in
many regards, not least of which, for us, is that it lacks policy items on both civil rights and cultural values.
We make only the most limited use of its results in the analysis that follows.
v
It would have been nice to have a counterpart analysis for one or more of the early postwar years, to be
sure that nothing had changed in the interim. Yet the fact that there are no counterpart items to behavioral
welfare in this earlier period is itself an unobtrusive measure of the situation in its time: survey analysts
were confident that ‘working-age welfare’ was what most people meant in the public debate over welfare
policy.
|
|
 Convention | | Convention is an application service for managing large or small academic conferences, annual meetings, and other types of events! | | Submission - Custom fields, multiple submission types, tracks, audio visual, multiple upload formats, automatic conversion to pdf. | | Review - Peer Review, Bulk reviewer assignment, bulk emails, ranking, z-score statistics, and multiple worksheets! | | Reports - Many standard and custom reports generated while you wait. Print programs with participant indexes, event grids, and more! | | Scheduling - Flexible and convenient grid scheduling within rooms and buildings. Conflict checking and advanced filtering. | | Communication - Bulk email tools to help your administrators send reminders and responses. Use form letters, a message center, and much more! | | Management - Search tools, duplicate people management, editing tools, submission transfers, many tools to manage a variety of conference management headaches! | | Click here for more information. |
|
|
|
| |
|
|
|
